catastrophic forgetting

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates ACL 2026 More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning WACV 2026 Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance CVPR 2026 Multi-Task Test-time Adaptation via Gradient Consensus and Plasticity Constraint AAAI 2026 New Metrics for Disambiguating Feature Overlap and Catastrophic Forgetting in Incremental Learning Contexts (Student Abstract) AAAI 2026 Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models CVPR 2026 OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting During Parameter-Efficient Fine-Tuning AAAI 2026 ORTCL: Towards Continual Learning of Time Series Foundation Models on Streaming Data via Orthogonal Rotation AAAI 2026 PANDA – Patch and Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning AAAI 2026 Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited Model Capacity CVPR 2026 Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning ACL 2026 Parameterized Prompt for Incremental Object Detection CVPR 2026 Parameter Merging with Gradient-Guided Supermasks in Online Continual Learning AAAI 2026 Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model AAAI 2026 Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification CVPR 2026 Protect to Adapt: Orthogonal Subspace Control with Ranked Negative-Prompt Curriculum for Few-Shot Action Recognition CVPR 2026 Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge AAAI 2026 Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning in Vision-Language Models CVPR 2026 Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning CVPR 2026 Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better Stability AAAI 2026 Re-evaluating Continual VQA: Toward Fair and Robust Evaluation for Multimodal Continual Learning CVPR 2026 Reinforcement Learning on Pre-Training Data ACL 2026 Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual Critics CVPR 2026 Robustness Under Data Scarcity: Few-Shot Continual Adversarial Training for Evolving Threats CVPR 2026 R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models AAAI 2026